跳过主要内容
评测来源/AA-Analyst Agent
参与排名专业工作

AA-Analyst Agent

Artificial Analysis · AA-Analyst Agent 的公开模型评测结果。

官方评测
来源说明

该来源测量模型在「专业工作」领域的具体交付表现,原始成绩会和统一能力读数分开展示。

限制: 不同版本、推理设置和测试集可能导致分数变化,请结合数据时间阅读。

使用方式

参与排名的来源会影响能力分;参考、交叉参考和观察来源仅用于对比与核验。

本来源的模型成绩

Claude Fable 5.10.57571.22026-11-05
Claude Sonnet 5.50.57571.22026-11-05
Claude Opus 5.50.562570.02026-11-05
Grok 4.70.5568.82026-10-18
Grok 4.70.5568.82026-10-17
Grok 4.70.5568.82026-11-05
Claude Opus 50.537567.62026-11-05
Claude Haiku 5.50.537567.62026-11-05
Claude Haiku 5.50.537567.62026-10-17
Claude Haiku 5.50.537567.62026-10-18
GPT-6 Astra0.512565.32026-11-05
GPT-5.50.564.12026-11-05
GPT-6.1 Sol0.564.12026-11-05
Claude Fable 50.487562.92026-11-05
Gemini 4 Argon0.487562.92026-10-18
Gemini 4 Argon0.487562.92026-10-17
Gemini 4 Argon0.487562.92026-11-05
GPT-5.6 Sol0.47561.72026-11-05
Claude Sonnet 50.462560.62026-11-05
Gemini 3.8 Flash0.462560.62026-10-18
Gemini 3.8 Flash0.462560.62026-10-17
Gemini 3.8 Flash0.462560.62026-11-05
Claude Opus 4.80.4559.42026-11-05
Claude Opus 4.70.437558.22026-11-05
GPT-6 Luna0.437558.22026-10-17
GPT-6 Luna0.437558.22026-11-05
GPT-6 Luna0.437558.22026-10-18
Gemini 3.1 Pro Preview0.412555.92026-11-05
Grok 4.60.412555.92026-11-05
Kimi K30.387553.52026-11-05
GLM 5.30.387553.52026-10-18
GLM 5.30.387553.52026-11-05
GLM 5.30.387553.52026-10-17
Muse Spark 1.30.37552.32026-11-05
Muse Spark 1.30.37552.32026-10-17
Muse Spark 1.30.37552.32026-10-18
MiMo V2.6 Pro0.37552.32026-11-05
MiMo V2.6 Pro0.37552.32026-10-17
MiMo V2.6 Pro0.37552.32026-10-18
Grok 4.50.3550.02026-11-05
DeepSeek V4.1 Flash0.3550.02026-10-18
DeepSeek V4.1 Flash0.3550.02026-11-05
DeepSeek V4.1 Flash0.3550.02026-10-17
Step 5 Preview0.3550.02026-11-05
Inkling Small0.27542.92026-11-05
GLM-5.3 Flash0.2540.62026-11-05
GLM-5.3 Flash0.2540.62026-10-17
GLM-5.3 Flash0.2540.62026-10-18
Inkling0.237539.42026-11-05
Claude Sonnet 4.60.235.82026-11-05
MiMo-V2.5-Pro0.235.82026-11-05
DeepSeek V4 Pro0.187534.72026-11-05
Qwen3.7 Max0.187534.72026-11-05
Claude Haiku 4.50.1531.12026-11-05
GPT-5.4 mini0.1531.12026-11-05
Mistral Medium 3.50.12528.82026-11-05
MiniMax-M2.70.112527.62026-11-05
MiniMax-M30.126.42026-11-05
Grok 4.30.087525.32026-11-05
Gemini 3.1 Flash Lite0.087525.32026-11-05
Nemotron 3 Ultra 550B A55B0.062522.92026-11-05

常见问题